A Multimodal Framework for Topic Propagation Classification in Social Networks

TL;DR

This work addresses the challenge of predicting topic propagation in social networks by proposing MPT-PropNet, a Transformer-based framework that fuses multidimensional features from user influence (UIR), sentiment (Text-CNN), temporal dynamics (Bi-LSTM), and propagation traces. The model introduces novel metrics (user relationship breadth and user authority) and replaces view counts with richer browsing traces to better capture dissemination patterns. Through extensive experiments on Twitter data across three topics, MPT-PropNet demonstrates superior $AUC$, $Recall$, and $FI$-Score compared to LR, Text-CNN, and GNN baselines, with ablation studies confirming the value of each module. The approach advances public opinion monitoring and online security by enabling more accurate, interpretable, and scalable topic propagation predictions in complex social networks.

Abstract

The rapid proliferation of the Internet and the widespread adoption of social networks have significantly accelerated information dissemination. However, this transformation has introduced complexities in information capture and processing, posing substantial challenges for researchers and practitioners. Predicting the dissemination of topic-related information within social networks has thus become a critical research focus. This paper proposes a predictive model for topic dissemination in social networks by integrating multidimensional features derived from key dissemination characteristics. Specifically, we introduce two novel indicators, user relationship breadth and user authority, into the PageRank algorithm to quantify user influence more effectively. Additionally, we employ a Text-CNN model for sentiment classification, extracting sentiment features from textual content. Temporal embeddings of nodes are encoded using a Bi-LSTM model to capture temporal dynamics. Furthermore, we refine the measurement of user interaction traces with topics, replacing traditional topic view metrics with a more precise communication characteristics measure. Finally, we integrate the extracted multidimensional features using a Transformer model, significantly enhancing predictive performance. Experimental results demonstrate that our proposed model outperforms traditional machine learning and unimodal deep learning models in terms of FI-Score, AUC, and Recall, validating its effectiveness in predicting topic propagation within social networks.

Figures (10)

• Figure : Fig.1.Idea Inspiration Process Diagram
• Figure : Fig.2.Processing of User Feature
• Figure : Fig.3.Overview of MPT-PropNet for social emotion prediction to online trending topics.
• Figure : Fig.4.Confusion matrices of MPT-PropNet on CostOfLiving.
• Figure : Fig.5.Confusion matrices of MPT-PropNet on Crypto.